Sparse Locations Research Articles

Flatness detection of super-flat emery floor based on terrestrial laser scanning

Traditional flatness detection method with 2-m ruler and feeler gauge can only manually measure to obtain data at sparse locations. Terrestrial Laser Scanning (TLS) has been widely used in the detection task of small-scale components. To overcome the time-consuming and laborious problem of traditional method and extend the application of TLS-based method, an efficient, full-coverage and intelligent TLS-based flatness detection method applicable to large-scale floors is presented in this paper to help with the acceptance of emery floor. An algorithm is designed to find the optimal position of ruler above the ground profile and measure the deviation between ruler and ground. The results of two comparison experiments demonstrates that the TLS-based method proposed in this paper has a high detection accuracy. In the detection task of a super-flat emery floor, floor plan labeled with pass rates can be easily obtained. Color maps marked with unqualified areas can be used as a guide for concrete polishing. By comparing row detection and column detection results, the pass rate is significantly directional in some conditions.

Snow depth time series Generation: Effective simulation at multiple time scales

Snow depth (SD) is a crucial variable of the water, energy, and nutrient cycles, impacting water quantity and quality, the occurrence of floods and droughts, snow-related hazards, and sub-surface ecological functions. As a result, quantifying SD dynamics is crucial for several scientific and practical applications. Ground measurements of SD provide information at sparse locations, and physical global model simulations provide information at relatively coarse spatial resolutions. An approach to complement this information is using stochastic models that generate time series of hydroclimatic variables, preserving their statistical properties in a computationally-effective manner. However, stochastic generation methods to produce SD time series exclusively do not exist in the literature. Here, we apply a stochastic model to produce synthetic daily SD time series trained by 448 stations in Canada. We show that the model captures key statistical properties of the observed records, including the daily distributions of zero and non-zero SD, temporal clustering (i.e., autocorrelation), and seasonal patterns. The model also excelled in capturing the observed higher-order L-moments at multiple temporal scales, with biases between simulated and observed L-skewness and L-kurtosis within (-0.1, +0.1) for 93.0 % and 98.3 % of the stations, respectively. The stochastic modelling approach introduced here advances the generation of SD time series, which are needed to develope Earth-system models and assess the risk of snowmelt flooding that lead to severe damage and fatalities.

Estimation of Temperature and Salinity from Marine Seismic Data—A Two-Step Approach

Ocean-water temperature and salinity are two vital properties that are required for weather-, climate-, and marine biology-related research. These properties are usually measured using disposable instruments at sparse locations, typically from tens to hundreds of kilometers apart. Laterally interpolating these sparse measurements provides smooth temperature and salinity distributions within the oceans, although they may not be very accurate. Marine seismic data, on the other hand, show visible reflections within the water-column which are primarily controlled by subtle sound-speed variations. Because these variations are functions of the temperature, salinity, and pressure, estimating sound-speed from marine seismic data and relating them to temperature and salinity have been attempted in the past. These seismically derived properties are of much higher lateral resolution (less than 25 m) than the sparse measurements and can be potentially used for climate and marine biology research. Estimating sound-speeds from seismic data, however, requires running iterative seismic inversions, which need a good initial model. Currently practiced ways to generate this initial model are computationally challenging, labor-intensive, and subject to human error and bias. In this research, we outline an automated method to generate the initial model which is neither computational and labor-intensive nor prone to human errors and biases. We also use a two-step process of, first, estimating the sound-speed from seismic inversion data and then estimating the salinity and temperature. Furthermore, by applying this method to real seismic data, we demonstrate the feasibility of our approach and discuss how the use of machine learning can further improve the computational efficiency of the method and make an impact on the future of climate modeling, weather prediction, and marine biology research.

Using an ex vivo MRI atlas of the human medial temporal lobe to characterize the 3D distribution of neurofibrillary tangle burden across histologically defined subregions

AbstractBackgroundAccumulation of tau neurofibrillary tangles (NFT) in the medial temporal lobe (MTL) is an early pathological change associated with neurodegeneration in Alzheimer’s Disease (AD). Current understanding of the spread of NFTs within the MTL is based on 2‐D histological sections sampled at sparse locations. Here, using human MTL specimens from donors with diagnoses spanning the AD continuum, we examine 3‐D quantitative maps of NFT burden derived from serial histology leveraging a high‐resolution, ex vivo MRI atlas, thus enabling more granular analyses.MethodWe combined ex vivo MRI scans (0.2×0.2×0.2mm3, 9.4T) of 55 MTL specimens using a customized registration approach to construct a 3‐D atlas (Ravikumar et al., Acta Neuropathol Comm, 2021). MTL subregions in the atlas were labelled based on cytoarchitecture using serial Nissl histology (n = 17) (Fig.1). For 25 specimens with a primary diagnosis of AD or primary age‐related tauopathy (78.6±10.9 years; 16M/9F), quantitative NFT burden maps were derived from serial anti‐tau immunohistochemistry histology and registered to the atlas for group‐level analysis (Yushkevich et al., Brain, 2021). For quantitative comparisons, we computed the mean NFT burden and cortical thickness within each subregion.ResultFig.2A shows average and summary frequency maps of NFT burden, computed separately for specimens with a low Braak stage (Braak0‐II; n = 11) and high Braak stage (BraakIV‐VI), that reveal a clear anterior‐to‐posterior gradient in NFT burden. At low Braak stages, we observe high levels of NFT burden in cornu ammonis (CA)1, entorhinal cortex (EC), and Brodmann area 35 (BA35;≈transentorhinal region), particularly in the outer cortical layers. CA1 and EC also show higher NFT burden relative to BA35 (Fig.2C). At high Braak stages, overall NFT burden is visibly higher and more widespread, with significant increases found across almost all subregions (Fig.2B). Moreover, significant correlations between NFT burden and cortical thinning were found in the perforant pathway (PP; molecular layer of the subiculum), dentate gyrus, EC and Areas TE, TF and TH (Fig.3).ConclusionBuilding on earlier work, we provide a detailed characterization of the distribution of NFT burden in the MTL. Our findings of specific subregional involvement of early NFT pathology can help inform the development of improved in vivo neuroimaging biomarkers

DeepBSL: 3-D Personalized Deep Binaural Sound Localization on Earable Devices

The prevalence of earable devices such as earbuds and headphones allows people to converse or listen to audio recordings on the move but often at the cost of reduced alertness of imminent health and safety threats in their surroundings. 3D Binaural Sound Localization (BSL), which aims to locate sound sources in space, plays a key role in improving one’s situation awareness. BSL on earable devices is inherently challenging due to the limited number of microphones available as well as subject-and location-dependent filtration effects of a person’s pinna, head and torso, described by Head-Related Transfer Functions (HRTFs). In this work, we develop DeepBSL, a deep neural network model to estimate azimuth and elevation angles of sound sources relative to a person’s head. For a new subject, an efficient procedure is developed to collect HRTFs at sparse locations using in-ear microphones and a mobile phone, which are then utilized to synthesize sounds of any type at arbitrary locations to train personalized DeepBSL models. Extensive evaluations using synthetic data from a public dataset and through real-world experiments demonstrate that the personalized DeepBSL models are data-efficient and can achieve better-than-human performances in BSL while significantly outperforming a state-of-art model that can only predict azimuth angles of sound sources. Our best performing model has an average azimuth prediction error of 2.9∘ (4.1∘) and elevation prediction error of 1.4∘ (2.9∘) in an indoor (outdoor) environment.

The utility of impact data in flood forecast verification for anticipatory actions: Case studies from Uganda and Kenya

AbstractSkilful flood forecasts have the potential to inform preparedness actions across scales, from smallholder farmers through to humanitarian actors, but require verification first to ensure such early warning information is robust. However, verification efforts in data‐scarce regions are limited to only a few sparse locations at pre‐existing river gauges. Hence, alternative data sources are urgently needed to enhance flood forecast verification to better guide preparedness actions. In this study, we assess the usefulness of less conventional data such as flood impact data for verifying flood forecasts compared with river‐gauge observations in Uganda and Kenya. The flood impact data contains semi‐quantitative and qualitative information on the location and number of reported flood events derived from five different data repositories (Dartmouth Flood Observatory, DesInventar, Emergency Events Database, GHB, and local) over the 2007–2018 period. In addition, river‐gauge observations from stations located within the affected districts and counties are used as a reference for verification of flood forecasts from the Global Flood Awareness System. Our results reveal both the potential and the challenges of using impact data to improve flood forecast verification in data‐scarce regions. From these, we provide a set of recommendations for using impact data to support anticipatory action planning.

Damage Localization in a Steel Truss Bridge Using Influence Lines Identified from Vehicle-Induced Acceleration

In the last few decades, structural health monitoring (SHM) has proven a helpful tool to support the maintenance and management of civil infrastructure. However, typical measurement networks are expensive and require considerable initial efforts. The user-friendliness and interpretability of the outcome of SHM systems are crucial factors in motivating infrastructure owners and decision-makers to sustain their costs. For this reason, simple algorithms that provide structural parameters with direct physical interpretability for professionals familiar with the typical quantities involved in structural engineering are still the most used in field applications. This paper proposes an original method to identify curvature influence lines of bridges and viaducts only using the structural acceleration response induced by vehicular loads. Acceleration time histories collected at sparse locations through standard accelerometers are employed. In contrast to SHM approaches based on modal parameters, the proposed method does not need strict synchronization, thus being suitable for wireless and low-cost monitoring solutions. Identified influence lines are used to define a spatially dense damage indicator for accurate localization of structural anomalies with a clear physical meaning. Experimental results obtained for a steel truss bridge analyzed in different damage conditions prove the efficacy of the proposed method for situations where modal-based approaches may fail.

Long-term river extent dynamics and transition detection using remote sensing: Case studies of Mekong and Ganga River

River dynamics are currently comprehensively studied at either a bankline or reach-scale level. Monitoring large-scale and long-term river extent dynamics provides fundamental insights relevant to the impact of climatic factors and anthropogenic activities on fluvial geomorphology. This study analyzed the two most populous rivers, Ganga and Mekong, to understand the river extent dynamics using 32 years of Landsat satellite data (1990–2022) in a cloud computing platform. This study categorizes river dynamics and transitions using the combination of pixel-wise water frequency and temporal trends. This approach can demarcate the river channel stability, areas affected by erosion and sedimentation, and the seasonal transitions in the river. The results illustrate that the Ganga river channel is found to be relatively unstable and very prone to meandering and migration as almost 40 % of the river channel has been altered in the past 32 years. The seasonal transitions, such as lost seasonal and seasonal to permanent changes are more prominent in the Ganga river, and the dominance of meandering and sedimentation in the lower course is also illustrated. In contrast, the Mekong river has a more stable course with erosion and sedimentation observed at sparse locations in the lower course. However, the lost seasonal and seasonal to permanent changes are also dominant in the Mekong river. Since 1990, Ganga and Mekong rivers have lost approximately 13.3 % and 4.7 % of their seasonal water respectively, as compared to the other transitions and categories. Factors such as climate change, floods, and man-made reservoirs could all be critical in triggering these morphological changes.

Sparse accelerometer-aided computer vision technology for the accurate full-field displacement estimation of beam-type bridge structures

Computer vision-based sensors are considered effective means to monitor full-field displacements; nevertheless, several limitations prevent their applications in full-scale structures. First, the accuracy of computer vision-based sensors is affected by measured distances. Second, due to the limited frame rate of cameras, computer vision-based sensors cannot record high-frequency responses. To effectively address these issues, a novel full-field displacement estimation approach based on the data fusion of camera-based measurements and limited accelerations was proposed. Full-field pseudo-static displacements were extracted from camera-based measurements, and full-field dynamic displacements were expanded by accelerations at sparse locations based on the modal superposition method. Subsequently, high-fidelity full-field displacements were obtained by data fusion. The proposed approach was numerically and experimentally verified. Further, the full-field displacements of an experimental-scale beam model and a full-scale bridge were estimated by a consumer-grade camera and several accelerometers.

Spintherobolus papilliferus in the rio Ribeira de Iguape basin: implications for the biogeography and conservation of an endangered species (Ostariophysi: Characiformes)

Abstract Spintherobolus papilliferus is an endangered characid endemic of the Atlantic Rainforest, known from sparse locations in the upper rio Tietê basin around the metropolitan area of São Paulo city, and from an affluent of rio Itapanhaú, a coastal stream in Bertioga, São Paulo State. In 2020, S. papilliferus was sampled from the rio Ribeira de Iguape basin in Juquitiba, São Paulo State, representing a new distributional record. We compared 17 morphometric and six meristic characters from all specimens with data from the rios Tietê and Itapanhaú. An overlap in the morphological data from the three populations was detected, except for five measure whose values are lower in rio Ribeira de Iguape. MANOVA and LDA revealed that this population differs significantly from the other two, showing shallower body and caudal peduncle, among other features. These morphological differences may be due to environmental selective pressures since rio Ribeira de Iguape drainage is marked by fast waters which can influence the shape of fish bodies over time. DNA-barcoding of all Spintherobolus species corroborate that the rio Ribeira de Iguape population belongs to S. papilliferus. We also present a hypothesis for the disjunct distribution of S. papilliferus involving headwater capture and discuss the implications for the conservation of this endangered species.

Development of economic processes utilizing solar energy

The concern of the electric utility companies to prioritize tight control on system performance is addressed in the paper as it immensely helps planning maintenance expenditure economically with customers’ expectations fully met. . The paper aims at making a comparative study of performance of the micro-grid power system with that of the interconnected micro-grid and national grid. A micro-grid that utilizes solar energy in sparse locations in hilly terrain for ensuring reliable electric supply to industrial houses engaged in product manufacturing processes has been considered. These manufacturing processes as a part of small and medium industries introduce goods and services necessary for securing economic growth and development in the country side where grid power supply is subject to frequent weather disturbances, and hence, very costly from the perspective of sustenance as well as maintenance. The solar energy trend has given scope for self-reliance and better livelihood of people who live away from cities but the products what they manufacture may be sent for consumption in the nearby cities. Thus, more and more dependence on the solar energy leads to nation’s economic growth policy. Moreover, it adds to uninterrupted and quality electric supply using clean energy in place of fossil fuels-based generation of electricity to protect environment; allows reducing health hazards and mitigating greenhouse gas emissions. Using reliability techniques, solar energy plant performance is quantitatively judged and compared with respect to the performance of the national grid supplying power supply to the remotely located population. The improved energy security, easy access and operational responses of the solar plant as a substitute to the grid power supply help develop economic growth of a nation.

Field-scale and site-specific permeability of sandstone reservoirs using a stabilized Monte Carlo algorithm: A case study

The permeability of sandstone varies significantly from site to site at the field scale. Well-established methods for permeability estimation depend on laboratory-measured parameters, which are available only at sparse locations. To overcome such dependency, we have developed a method to estimate sandstone’s site-specific and field-scale permeability using well log and interconnected porosity data, respectively. We have considered sandstone as a mono-dispersed porous medium with monofractal pores and simulated them using the fractal theory-based acceptance-rejection Monte Carlo algorithm. Stabilization of the algorithm through an error convergence scheme generated repeatable and reliable permeability values. We tested this developed method on cores from various formations representing clean/shaly sandstones and a few sandstone samples contaminated by carbonates. Compared to laboratory-measured permeability, the estimates are within one-order magnitude error bounds for clean/shaly sandstones and higher for samples that are either contaminated by carbonates or have higher pore volume normalized surface area. We applied the method to infer field-scale permeability trend to explain the unexpected movement of hydrocarbons in the Kalol reservoir lying in the Balol oil field of Cambay Basin India, where the in-situ combustion enhanced oil recovery process is implemented. The field-scale permeability trend could explain the northward movement of the hydrocarbons to the adjacent oil field, Lanwa. It was also observed in the production data of the Lanwa field that the in-situ combustion in Balol has benefited oil production in its wells.

Estimating sonic boom metrics across a community using a Kalman filter

As part of the Quesst mission, NASA will fly the X-59 aircraft over selected communities to evaluate community responses to low-intensity sonic booms. The purpose of these community tests is to determine the dose-response relationship between the noise exposure metrics and the community response. The independent variables for the dose-response relationship are the noise exposure metrics experienced by survey respondents within the community. Two sources of noise exposure metrics are available in each community: measurements at sparse locations throughout the community, and calculations from propagation models across the community. Both the measurements and calculations are subject to uncertainty. A Kalman filter is proposed to combine the measured and calculated noise exposure metrics to obtain the best estimate of the true noise exposure metrics across the community. The noise exposure metrics estimated by the Kalman filter have lower uncertainty than either the measured or calculated noise exposure metrics alone. Simulations demonstrate that the Kalman filter produces a more accurate estimate of the true noise exposure metrics than other noise estimation methods.

An Image-Based Deep Learning Approach with Improved DETR for Power Line Insulator Defect Detection

Insulators are basic parts of high-voltage transmission, and detecting faults of insulators is a critical task. Most state-of-the-art methods contain two or more stages, including insulator detection and defect locating. Some also involve hand-designed components to improve the performance due to the complicated and misleading background of the wild. To automatically detect faults in UAV-captured insulator images, this paper presents a method that introduces DETR into insulator defect detection. With the self-attention mechanism in Transformer, the model can naturally exploit its advantage in focusing on the target area. However, training DETR requires large data sets and long training schedules to establish spatial relations in sparse locations, which makes it generally not feasible to train in small data sets. To explore the possibility of training a well-performing model with a data set that minimizes the cost of collecting insulator images, transfer learning techniques were applied to this process. To compensate for the disadvantage of DETR in detecting small objects at more precise scales, an improved loss was transplanted to this model. The results show that our proposed method can detect defects directly from UAV images without the need to locate the insulator first, while providing competitive performance with a lower cost of collecting training samples.

Full-field temperature recovery during water quenching processes via physics-informed machine learning

Water quenching is an effective heat treatment process to produce high-quality metallic structures. Accurate and efficient prediction of the full-field temperature inside the part to capture and control the residual stresses and part quality remains a challenging task. This paper proposes a simple and easy-to-use model for full-field temperature recovery during water quenching processes , using physics-informed machine learning (ML). The novelty of the ML framework is that it only needs temperature measurements of sparse locations to efficiently/accurately recover the full spatio-temporal temperature field without invoking sophisticated multiphysics simulations. The ML framework consists of two tightly connected neural network (NN) models: (1) Firstly, a physics-informed neural network (PINN)-based surrogate model is constructed. The surrogate model, which approximates a high-fidelity finite element model , is responsible for quickly outputting the full-field temperature distribution from the parameterized thermal boundary conditions (BCs). (2) Then, another neural network is constructed to project the available experimental data onto the surrogate model and learn the optimal thermal BC from the parametric space , which produces the best full-field temperature prediction in the surrogate model. The proposed ML framework features high efficiency, accuracy, and universality for temperature prediction in quenching processes. These features are carefully demonstrated and the framework is validated using experimental measurements.

Machine learning approach to prediction of real-time ocean sound speed profile

Sound speed profile (SSP) determines sound propagation in the ocean. Variation of sound speed profiles with time and location heavily impacts underwater sonar systems used in ocean science and engineering. However, mapping sound speed profile over a vast area of the oceans in real-time is impossible by the traditional way, where sound speed is calculated from insitu profiling measurements of temperature, salinity, and pressure, which is expensive and, therefore, limited in sparse locations and time. Here, we aim to develop a machine learning model to predict real-time sound speed profiles anywhere in the global oceans. Our model takes advantage of the big data of long-term global temperature, salinity, and pressure measurements and further accounts for the variability of the surface ocean by inputting sea surface temperature and sea surface salinity data, which can be updated by satellite remote sensing in real-time. Here, SSPs are predicted for Pacific, Atlantic, and Indian ocean regions. The results show that the estimated SSPs had a root-mean-square error of 0.26 m/s and a coefficient of determination of 0.99. About 99% of the estimates lie within ±0.4 m/s of the SSPs obtained from in situ temperature and salinity profiles.

Prediction of the ocean water sound speeds via attribute-guided seismic waveform inversion

Oceanic temperature and salinity are important for studying ocean dynamics and marine ecosystems, and for developing climate prediction models. Physical oceanographers measure these properties using expendable instruments, providing accurate measurements at high vertical resolution at sparse lateral locations. Accuracy of these temperature and salinity data when laterally interpolated and used for ocean dynamics, marine biology, and weather-related studies is questionable. Marine seismic data indicate visible reflections within the water columns, which, in turn, are primarily controlled by the vertical and lateral variations of the ocean water sound speeds. Because these sound-speed variations are functions of temperature and salinity, water-column seismic reflection data have been inverted for sound speeds and used to estimate temperature and salinity. These seismically derived temperature and salinity data have lower vertical, but much finer lateral resolution than those measured by expendable instruments, and therefore are useful for physical oceanography, marine biology, and climate research. However, quality of the seismic inversion relies on a good initial model, which requires generating models at sparse locations over 2D or 3D seismic data volumes and interpolating them over the horizon, manually picked from the stacked seismic data. Because horizon picking is subject to human error and bias, replacing it with an automated process is desirable. We outline a new attribute-guided methodology for initial model generation where no horizon picking is necessary. Starting with this initial model, we run prestack waveform inversion based on genetic algorithm optimization and demonstrate that our method can predict reliable sound-speed profiles. We conclude that our method is a good way for estimating ocean water sound speeds and relating them to the temperature and salinity.

Interpolation of Precipitation Extremes on a Large Domain Toward IDF Curve Construction at Unmonitored Locations

An intensity–duration–frequency (IDF) curve describes the relationship between rainfall intensity and duration for a given return period and location. Such curves are obtained through frequency analysis of rainfall data and commonly used in infrastructure design, flood protection, water management, and urban drainage systems. However, they are typically available only in sparse locations. Data for other sites must be interpolated as the need arises. This paper describes how extreme precipitation of several durations can be interpolated to compute IDF curves on a large, sparse domain. In the absence of local data, a reconstruction of the historical meteorology is used as a covariate for interpolating extreme precipitation characteristics. This covariate is included in a hierarchical Bayesian spatial model for extreme precipitations. This model is especially well suited for a covariate gridded structure, thereby enabling fast and precise computations. As an illustration, the methodology is used to construct IDF curves over Eastern Canada. An extensive cross-validation study shows that at locations where data are available, the proposed method generally improves on the current practice of Environment and Climate Change Canada which relies on a moment-based fit of the Gumbel extreme-value distribution.

Deep-learning spatial principles from deterministic chemical transport models for chemical reanalysis: an application in China for PM<sub>2.5</sub>

Abstract. Well-estimated air pollutant concentration fields are critically important to compensate for observations that are only sparsely available, especially over non-urban areas. Previous data fusion methods generally used statistical models to relate observations of target variables to proxy data and supporting variables at known stations. In this study, we developed a new data fusion paradigm by designing a deep-learning model framework and workflow to learn multivariable spatial correlations from chemical transport model (CTM) simulations, before using it to estimate PM2.5 reanalysis fields from station observations. The model was composed of two modules as an explainable PointConv operation to pre-process isolated observations and a regression grid-to-grid network to build correlations among multiple variables. The model was trained with only CTM simulations and supporting geographical covariates. The trained model was evaluated in two aspects of (1) reproducing raw PM2.5 CTM simulations and (2) generating reanalysis and fused PM2.5 fields. First, the model was able to reproduce the CTM simulations well on a full domain from sampled CTM data items at sparse locations with an average R2=0.94 and RMSE = 4.85 µg m−3. Second, the fused PM2.5 fields estimated from observations achieved a good performance with R2=0.77 (RMSE = 14.29 µg m−3) and R2=0.84 (RMSE = 12.96 µg m−3) respectively evaluated at the stringent city level and station level. The generated reanalysis PM2.5 fields have complete spatial coverage within the modeling domain. One significant benefit of the fusion framework is that the model training does not rely on observations, which can be used to predict PM2.5 fields in newly set up observation networks such as those using portable sensors. Meanwhile, in the prediction procedure, only station observations are used along with supporting covariates. The fusion model has high computing efficiency (< 1 s d−1) due to acceleration using a graphical processing unit (GPU). As an alternative to generate chemical reanalysis fields, the method can be readily implemented in near-real time and be universally applied for other simulated variables with measurements available.

A graph-matching approach for cross-view registration of over-view and street-view based point clouds

Wide-area 3D data generation for complex urban environments often needs to leverage a mixed use of data collected from both air and ground platforms, such as from aerial surveys, satellite, and mobile vehicles. On one hand, such kind of data with information from drastically different views (ca. 90° and more) forming cross-view data, which due to very limited overlapping region caused by the drastically different line of sight of the sensors, is difficult to be registered without significant manual efforts. On the other hand, the registration of such data often suffers from non-rigid distortion of the street-view data (e.g., non-rigid trajectory drift), which cannot be simply rectified by a similarity transformation. In this paper, based on the assumption that the object boundaries (e.g., buildings) from the over-view data should coincide with footprints of façade 3D points generated from street-view photogrammetric images, we aim to address this problem by proposing a fully automated geo-registration method for cross-view data, which utilizes semantically segmented object boundaries as view-invariant features under a global optimization framework through graph-matching: taking the over-view point clouds generated from stereo/multi-stereo satellite images and the street-view point clouds generated from monocular video images as the inputs, the proposed method models segments of buildings as nodes of graphs, both detected from the satellite-based and street-view based point clouds, thus to form the registration as a graph-matching problem to allow non-rigid matches; to enable a robust solution and fully utilize the topological relations between these segments, we propose to address the graph-matching problem on its conjugate graph solved through a belief-propagation algorithm. The matched nodes will be subject to a further optimization to allow precise-registration, followed by a constrained bundle adjustment on the street-view image to keep 2D-3D consistencies, which yields well-registered street-view images and point clouds to the satellite point clouds. Our proposed method assumes no or little prior pose information (e.g. very sparse locations from consumer-grade GPS (global positioning system)) for the street-view data and has been applied to a large cross-view dataset with significant scale difference containing 0.5 m GSD (Ground Sampling Distance) satellite data and 0.005 m GSD street-view data, 1.5 km in length involving 12 GB of data. The experiment shows that the proposed method has achieved promising results (1.27 m accuracy in 3D), evaluated using collected LiDAR point clouds. Furthermore, we included additional experiments to demonstrate that this method can be generalized to process different types of over-view and street-view data sources, e.g., the open street view maps and the semantic labeling maps. Codes will be made available through Github Repository.1https://github.com/GDAOSU/graph-matching-based-crossview-registration.1